基于规则的航空发动机孔探图像诊断方法研究

针对军用航空发动机内部损伤频率高、诊断决策时间长的问题,运用基于规则的推理方法,结合案例推理,进行了航空发动机内部损伤维修决策的专家诊断研究,开发了基于孔探图像的航空发动机内部损伤维修决策专家系统。依据领域专家的经验,通过分析得到了对该型发动机的专家知识,并将其转换为if-then的知识规则存放于知识库中;利用图像处理方法,对损伤进行测量,得到损伤的尺寸参数;根据损伤尺寸,依据相应的知识规则,应用正向推理得到损伤的维修决策。运用多个航空发动机内部损伤实例验证了所开发的专家系统的有效性。     

Space,Language, and Ontology: A Response to Bateman

Abstract

Some of John Bateman's critiques of my article “Qualitative Spatial Reasoning in Interpreting Text and Narrative” are certainly valid. However, the alternative solutions that he proposes do not seem to me to be improvements.     

Managing Temporal Constraints with Preferences

Abstract

Preferences in temporal problems are common but significant in many real world applications. In this paper, we extend our temporal reasoning framework, managing numeric and symbolic information, in order to handle preferences. Unlike the existing models managing single temporal preferences, ours supports four types of preferences, namely: numeric and symbolic temporal preferences, composite preferences and conditional preferences. This offers more expressive power in representing a wide variety of temporal constraint problems. The preferences are considered here as a set of soft constraints using a c-semiring structure with combination and projection operators. Solving temporal constraint problems with preferences consists in finding a solution satisfying all the temporal constraints while optimizing the preference values. This is handled by a variant of the branch and bound algorithm, we propose in this paper, and where constraint propagation is used to improve the time efficiency. Experimental tests, we conducted on randomly generated temporal constraint problems with preferences, favor a variant of MAC as the constraint propagation strategy that should be used within the branch and bound algorithm.     

Mereological inheritance

In recent investigations of Spatial Reasoning, SpatialKnowledge Representation, and Geographic Information Systems, asignificant effort has been spent by many scholars of the areaabout the problem of representing properties of spatial objects bymeans of logical theories.An analogous effort has been the problem of analyzingthe qualitative relations which can be established between twospace regions. These investigations have led to a generalframework of the field known by the term ``mereo-topology'.Though both the above mentioned approaches have proved to besuccessful in the investigation of formal and practically relevantaspects of spatial objects, no attempt has been carried out in the direction of integrating the approaches and looking at the relationshipbetween a general logical theory of space and mereo-topology from an analytical point of view, in particular for exploiting thecombinatorial behaviour of such an integrated model.This paper intends to fill the gap and analyze the behaviour ofspatial formulae of a logical theory of space as objects which canbe classified based on the behaviour they exhibit with respect tothe parts and supertparts of the regions where they are true. Wename these categories of behaviourinheritance modalities.     

一类含小参数微分方程鸭解的存在性

本文应用微分方程定性理论、 渐进分析方法、 隐函数定理以及不动点理论的方法研究一类单参数二维奇异摄动系统.给出了当系统的奇点在破坏点的小邻域时鸭解和鸭极限环存在的充分条件.证明了存在参数值a=a\-c(ε),使得对a\-c(ε)小邻域中的所有参数a, 系统存在鸭极限环.并给出了鸭解和鸭极限环的渐近估计式以及鸭极限环随参数变化的规律.本文推广了文献[1]和文献[2]的结果.     

卫星天线振动信息融合试验研究

讨论了D -S证据推理理论 ,给出了传感器特征信息融合算法。结合卫星天线振动频率分配控制问题 ,进行相应的实验研究 ,对传感器的特征信息进行融合 ,给出了振动响应频率特征信息提取方法 ,剔除边界条件对测试结果置信度的影响     

三级倒立摆的数控稳定

 应用基于物理模型的拟人智能控制思想设计控制器.结合单倒立摆系统模型的定性分析与三级倒立摆物理结构特性分析得到定性控制律,利用系统运动模态随反馈增益系数的转化规律,由智能搜索方法实现定性控制律的量化,成功实现计算机控制三级倒立摆系统长时间稳定,并给出各状态变量实测数据曲线图.应用同样方法可以控制不同结构的三级倒立摆稳定.证实了所采用方法的有效性和实验成果的可重复性.     

基于RBR与CBR的维修大纲专家系统

根据飞机维修大纲研制的需要,依据最新的维修指导小组思想和类似机型的维修大纲经验,提出了基于规则推理(RBR)和案例推理(CBR)相结合的民机维修大纲制订方法.构建了民机维修大纲专家系统的总体框架,并对该系统中的关键技术问题——案例的表示和组织、案例的检索、集成推理技术和案例的修正与存储进行了详细分析和研究.案例的检索分两步进行:首先从案例库中找出与新机型尽可能相似的机型,然后,从类似机型中进一步匹配出最相似的项目.集成推理采用RBR和CBR分开推理,再比较结果做出决策.最后,采用面向对象的程序设计方法对该专家系统编程,并以某航空公司飞机验证了RBR和CBR相结合的维修大纲制订方法的有效性.      

基于桶消元的数控机床故障模糊贝叶斯网络推理方法

用模糊数描述节点的多种故障状态,用模糊子集描述根节点的故障概率,用贝叶斯网络的条件概率表描述节点间的不确定关系,构建数控机床故障的模糊贝叶斯网络;采用桶消元算法,对数控机床故障的模糊贝叶斯网络进行推理和计算,获得根节点的后验概率,为数控机床故障诊断与分析提供依据;最后,以数控机床刀架系统故障的贝叶斯网络推理过程为例,验证所提理论和方法的有效性。